入侵检测中支持向量机参数选择方法研究

In order to construct an intrusion detection classifier based on support vector machines (SVM) that has good learning and generalization ability, the construction of the SVM classifier and the effect of SVM parameter are discussed. A new method for quickly selecting the parameters of SVM is presented. And the steps of the SVM parameters selecting are given. Experiments on KDD Cup 99 network intrusion detection dataset indicate that the proposed method can speed up the process of constructing an intrusion detection classifier and the detection accuracy for intrusion is higher.